© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57011
    Prev
    Next
    INDEX
    Explanations

    background color or image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nado
    -0.09
    ollo
    -0.09
    ((__
    -0.09
    説
    -0.08
    ISED
    -0.08
    utri
    -0.08
    jaw
    -0.08
    ä¸įå¿«
    -0.08
    æ³Ľ
    -0.08
    odob
    -0.07
    POSITIVE LOGITS
    abal
    0.07
    Ø·ÙĦ
    0.06
    ämp
    0.06
     perceb
    0.06
    梨
    0.06
    Screenshot
    0.06
    åĭº
    0.05
     попаданиÑı
    0.05
    ãĢģ
    0.05
    åĬ©åѦ
    0.05
    Activations Density 0.025%

    No Known Activations